jcyhcs

hi.professor: like the topic said, please help!

hi,progessor: like the topic said,please help!

not use libtorch for deployment solov2 tensorrt?

1

hi,professor: is there any possible for deployment solov2 don't use libtorch? just use tensorrt deserialize api, then write some postprocess code? beacause it has fewer dependence, install libtorch on jetson...

compile error!

1

hi,professor: when i compile (build_model , i got error: Solov2-TensorRT-CPP/InstanceSegment/common.h:388:9: error: ‘virtual nvinfer1::IBuilder::~IBuilder()’ is protected within this context delete obj; ^~~~~~ why? my enviroment: nvidia jetson tx2 with jetpack4.5.1 tensorrt...

please optimize the code with only cpu,

hi,professor: i run your project code on jetson xavier nx, can show mesh successful, but i mentioned that the mesh gpu always grew up, why? please help me!

感谢您的工作和奉献，这个工程您还在继续维护吗？能给出yolov4后处理部分代码吗？我调试了很久，yolov4的检测效果很差，觉得是和后处理部分代码有关。

yolov4 需要修改parseYolov3Feature这个函数吗？

3

大佬你好，我将yolov4模型转化成了nnie wk文件，利用nnie-lite进行推理的时候，我修改了anchors部分，修改如下：  请问 这个函数还修改吗？如果需要，怎么修改呢？

博主的yolov3我在hi3519av100平台下运行调试通过，请问能提供yolov4的支持吗？